Check Trajectory Abort

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds valuable context beyond the annotations: the purpose of preventing token burn, the evaluation against attempt history, and the full return shape (should_abort, abort_probability, action, reasoning_summary) despite no output schema being present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, then uses clear 'Use when', 'Do NOT use when', and 'Returns' sections. Every sentence is purposeful and the structure makes scanning easy for an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, read-only guard tool with no output schema, the description covers purpose, usage conditions, exclusions, and return fields thoroughly. Nothing essential for correct invocation or interpretation appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters (proposed_step and recent_attempts_summary) are already documented in the schema. The description mirrors these concepts ('proposed plan', 'recent attempt history') but adds no syntax, format, or example that would deepen parameter understanding. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it guards against doom loops, circular retries, dead-ends, and destructive refactoring by evaluating a proposed plan against recent attempt history. This is clearly distinct from siblings like triage, route, verify, modulate, and nudge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use the tool (before retrying a failed step, executing a code edit after failures, or attempting a potentially circular fix) and when not to use it (first attempt on a fresh task with no prior failure history). This is exactly the kind of routing guidance an agent needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.